FDA Addresses Issues with the Use of Multiple Endpoints in Final Guidance
Seeking to help sponsors avoid making false efficacy conclusions in drug and biologic trials that use multiple endpoints, the FDA has published final guidance on grouping and ordering endpoints for analysis and statistical approaches for managing them.
Regulatory concerns about multiple endpoints generally come up in trials aimed at showing effectiveness to support drug approval and claims in FDA-approved labeling. “However, this issue is important for trials throughout the drug development process,” the agency said.
The guidance includes a detailed section on general principles behind the use of multiple endpoints that sponsors should consider, including the different ways of grouping endpoints, controlling Type I error rates, Type II error rates and sample size, the hierarchical grouping of endpoints in trials and the individual components of composite and multicomponent endpoints.
It also includes an appendix containing a number of common statistical methods that work well with multiple endpoints, as well as a section of general references.
“There are many strategies and methods that can be used, as appropriate, as described in this guidance,” the FDA said. “Each of these methods has advantages and disadvantages and the selection of suitable strategies and methods is a challenge that should be addressed at the study-planning stage. Statistical expertise should be enlisted to help choose the most appropriate approach.”
The guidance notes that the FDA’s recommendations for multiple endpoints and “multiplicity” generally apply to other areas as well, including the use of multiple doses, time points and study population subgroups, though the guidance does not cover these specifically. It also notes that different considerations may come into play in certain unique situations, such as the evaluation of multiple drugs for a single disease in a master protocol.
Access the full final guidance here: https://bit.ly/3Difj0N.